Merge tag 'mlx5-shared-2017-08-07' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

Saeed Mahameed says:

====================
mlx5-shared-2017-08-07

This series includes some mlx5 updates for both net-next and rdma trees.

From Saeed,
Core driver updates to allow selectively building the driver with
or without some large driver components, such as
	- E-Switch (Ethernet SRIOV support).
	- Multi-Physical Function Switch (MPFs) support.
For that we split E-Switch and MPFs functionalities into separate files.

From Erez,
Delay mlx5_core events when mlx5 interfaces, namely mlx5_ib, registration
is taking place and until it completes.

From Rabie,
Increase the maximum supported flow counters.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

75 files changed, 725 insertions, 271 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a208bfe367b5..61a0cb15067e 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -380,7 +380,7 @@ config ARCH_EP93XX
 	bool "EP93xx-based"
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARM_AMBA
-	select ARM_PATCH_PHYS_VIRT
+	imply ARM_PATCH_PHYS_VIRT
 	select ARM_VIC
 	select AUTO_ZRELADDR
 	select CLKDEV_LOOKUP
diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts
index 895fa6cfa15a..563901e0ec07 100644
--- a/arch/arm/boot/dts/armada-388-gp.dts
+++ b/arch/arm/boot/dts/armada-388-gp.dts
@@ -75,7 +75,7 @@
 					pinctrl-names = "default";
 					pinctrl-0 = <&pca0_pins>;
 					interrupt-parent = <&gpio0>;
-					interrupts = <18 IRQ_TYPE_EDGE_FALLING>;
+					interrupts = <18 IRQ_TYPE_LEVEL_LOW>;
 					gpio-controller;
 					#gpio-cells = <2>;
 					interrupt-controller;
@@ -87,7 +87,7 @@
 					compatible = "nxp,pca9555";
 					pinctrl-names = "default";
 					interrupt-parent = <&gpio0>;
-					interrupts = <18 IRQ_TYPE_EDGE_FALLING>;
+					interrupts = <18 IRQ_TYPE_LEVEL_LOW>;
 					gpio-controller;
 					#gpio-cells = <2>;
 					interrupt-controller;
diff --git a/arch/arm/boot/dts/da850-evm.dts b/arch/arm/boot/dts/da850-evm.dts
index a423e8ebfb37..67e72bc72e80 100644
--- a/arch/arm/boot/dts/da850-evm.dts
+++ b/arch/arm/boot/dts/da850-evm.dts
@@ -301,25 +301,4 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&vpif_capture_pins>, <&vpif_display_pins>;
 	status = "okay";
-
-	/* VPIF capture port */
-	port@0 {
-		vpif_input_ch0: endpoint@0 {
-			reg = <0>;
-			bus-width = <8>;
-		};
-
-		vpif_input_ch1: endpoint@1 {
-			reg = <1>;
-			bus-width = <8>;
-			data-shift = <8>;
-		};
-	};
-
-	/* VPIF display port */
-	port@1 {
-		vpif_output_ch0: endpoint {
-			bus-width = <8>;
-		};
-	};
 };
diff --git a/arch/arm/boot/dts/da850-lcdk.dts b/arch/arm/boot/dts/da850-lcdk.dts
index b837fec70eec..a0f0916156e6 100644
--- a/arch/arm/boot/dts/da850-lcdk.dts
+++ b/arch/arm/boot/dts/da850-lcdk.dts
@@ -318,11 +318,4 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&vpif_capture_pins>;
 	status = "okay";
-
-	/* VPIF capture port */
-	port {
-		vpif_ch0: endpoint {
-			  bus-width = <8>;
-		};
-	};
 };
diff --git a/arch/arm/boot/dts/dm8168-evm.dts b/arch/arm/boot/dts/dm8168-evm.dts
index 1865976db5f9..c72a2132aa82 100644
--- a/arch/arm/boot/dts/dm8168-evm.dts
+++ b/arch/arm/boot/dts/dm8168-evm.dts
@@ -68,6 +68,34 @@
 			DM816X_IOPAD(0x0d08, MUX_MODE0)			/* USB1_DRVVBUS */
 		>;
 	};
+
+	nandflash_pins: nandflash_pins {
+		pinctrl-single,pins = <
+			DM816X_IOPAD(0x0b38, PULL_UP | MUX_MODE0)		/* PINCTRL207 GPMC_CS0*/
+			DM816X_IOPAD(0x0b60, PULL_ENA | MUX_MODE0)		/* PINCTRL217 GPMC_ADV_ALE */
+			DM816X_IOPAD(0x0b54, PULL_UP | PULL_ENA | MUX_MODE0)	/* PINCTRL214 GPMC_OE_RE */
+			DM816X_IOPAD(0x0b58, PULL_ENA | MUX_MODE0)		/* PINCTRL215 GPMC_BE0_CLE */
+			DM816X_IOPAD(0x0b50, PULL_UP | MUX_MODE0)		/* PINCTRL213 GPMC_WE */
+			DM816X_IOPAD(0x0b6c, MUX_MODE0)				/* PINCTRL220 GPMC_WAIT */
+			DM816X_IOPAD(0x0be4, PULL_ENA | MUX_MODE0)		/* PINCTRL250 GPMC_CLK */
+			DM816X_IOPAD(0x0ba4, MUX_MODE0)				/* PINCTRL234 GPMC_D0 */
+			DM816X_IOPAD(0x0ba8, MUX_MODE0)				/* PINCTRL234 GPMC_D1 */
+			DM816X_IOPAD(0x0bac, MUX_MODE0)				/* PINCTRL234 GPMC_D2 */
+			DM816X_IOPAD(0x0bb0, MUX_MODE0)				/* PINCTRL234 GPMC_D3 */
+			DM816X_IOPAD(0x0bb4, MUX_MODE0)				/* PINCTRL234 GPMC_D4 */
+			DM816X_IOPAD(0x0bb8, MUX_MODE0)				/* PINCTRL234 GPMC_D5 */
+			DM816X_IOPAD(0x0bbc, MUX_MODE0)				/* PINCTRL234 GPMC_D6 */
+			DM816X_IOPAD(0x0bc0, MUX_MODE0)				/* PINCTRL234 GPMC_D7 */
+			DM816X_IOPAD(0x0bc4, MUX_MODE0)				/* PINCTRL234 GPMC_D8 */
+			DM816X_IOPAD(0x0bc8, MUX_MODE0)				/* PINCTRL234 GPMC_D9 */
+			DM816X_IOPAD(0x0bcc, MUX_MODE0)				/* PINCTRL234 GPMC_D10 */
+			DM816X_IOPAD(0x0bd0, MUX_MODE0)				/* PINCTRL234 GPMC_D11 */
+			DM816X_IOPAD(0x0bd4, MUX_MODE0)				/* PINCTRL234 GPMC_D12 */
+			DM816X_IOPAD(0x0bd8, MUX_MODE0)				/* PINCTRL234 GPMC_D13 */
+			DM816X_IOPAD(0x0bdc, MUX_MODE0)				/* PINCTRL234 GPMC_D14 */
+			DM816X_IOPAD(0x0be0, MUX_MODE0)				/* PINCTRL234 GPMC_D15 */
+		>;
+	};
 };
 
 &i2c1 {
@@ -90,6 +118,8 @@
 
 &gpmc {
 	ranges = <0 0 0x04000000 0x01000000>;	/* CS0: 16MB for NAND */
+	pinctrl-names = "default";
+	pinctrl-0 = <&nandflash_pins>;
 
 	nand@0,0 {
 		compatible = "ti,omap2-nand";
@@ -98,9 +128,11 @@
 		interrupt-parent = <&gpmc>;
 		interrupts = <0 IRQ_TYPE_NONE>, /* fifoevent */
 			     <1 IRQ_TYPE_NONE>; /* termcount */
+		rb-gpios = <&gpmc 0 GPIO_ACTIVE_HIGH>; /* gpmc_wait0 */
 		#address-cells = <1>;
 		#size-cells = <1>;
 		ti,nand-ecc-opt = "bch8";
+		ti,elm-id = <&elm>;
 		nand-bus-width = <16>;
 		gpmc,device-width = <2>;
 		gpmc,sync-clk-ps = <0>;
@@ -164,7 +196,7 @@
 	vmmc-supply = <&vmmcsd_fixed>;
 	bus-width = <4>;
 	cd-gpios = <&gpio2 7 GPIO_ACTIVE_LOW>;
-	wp-gpios = <&gpio2 8 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 8 GPIO_ACTIVE_HIGH>;
 };
 
 /* At least dm8168-evm rev c won't support multipoint, later may */
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index 59cbf958fcc3..566b2a8c8b96 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/arch/arm/boot/dts/dm816x.dtsi
@@ -145,7 +145,7 @@
 		};
 
 		elm: elm@48080000 {
-			compatible = "ti,816-elm";
+			compatible = "ti,am3352-elm";
 			ti,hwmods = "elm";
 			reg = <0x48080000 0x2000>;
 			interrupts = <4>;
diff --git a/arch/arm/boot/dts/dra71-evm.dts b/arch/arm/boot/dts/dra71-evm.dts
index 4d57a55473af..a6298eb56978 100644
--- a/arch/arm/boot/dts/dra71-evm.dts
+++ b/arch/arm/boot/dts/dra71-evm.dts
@@ -190,7 +190,7 @@
 		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
 		ti,tx-internal-delay = <DP83867_RGMIIDCTL_250_PS>;
 		ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_8_B_NIB>;
-		ti,impedance-control = <0x1f>;
+		ti,min-output-impedance;
 	};
 
 	dp83867_1: ethernet-phy@3 {
@@ -198,7 +198,7 @@
 		ti,rx-internal-delay = <DP83867_RGMIIDCTL_2_25_NS>;
 		ti,tx-internal-delay = <DP83867_RGMIIDCTL_250_PS>;
 		ti,fifo-depth = <DP83867_PHYCR_FIFO_DEPTH_8_B_NIB>;
-		ti,impedance-control = <0x1f>;
+		ti,min-output-impedance;
 	};
 };
 
diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi
index 497a9470c888..5739389f5bb8 100644
--- a/arch/arm/boot/dts/exynos4.dtsi
+++ b/arch/arm/boot/dts/exynos4.dtsi
@@ -59,6 +59,9 @@
 		compatible = "samsung,exynos4210-audss-clock";
 		reg = <0x03810000 0x0C>;
 		#clock-cells = <1>;
+		clocks = <&clock CLK_FIN_PLL>, <&clock CLK_FOUT_EPLL>,
+			 <&clock CLK_SCLK_AUDIO0>, <&clock CLK_SCLK_AUDIO0>;
+		clock-names = "pll_ref", "pll_in", "sclk_audio", "sclk_pcm_in";
 	};
 
 	i2s0: i2s@03830000 {
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 2484f11761ea..858e1fed762a 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -1126,8 +1126,8 @@
 		};
 	};
 
-	gpu: mali@ffa30000 {
-		compatible = "rockchip,rk3288-mali", "arm,mali-t760", "arm,mali-midgard";
+	gpu: gpu@ffa30000 {
+		compatible = "rockchip,rk3288-mali", "arm,mali-t760";
 		reg = <0xffa30000 0x10000>;
 		interrupts = <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm/boot/dts/sun8i-a83t.dtsi b/arch/arm/boot/dts/sun8i-a83t.dtsi
index 8923ba625b76..19a8f4fcfab5 100644
--- a/arch/arm/boot/dts/sun8i-a83t.dtsi
+++ b/arch/arm/boot/dts/sun8i-a83t.dtsi
@@ -44,7 +44,9 @@
 
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 
+#include <dt-bindings/clock/sun8i-a83t-ccu.h>
 #include <dt-bindings/clock/sun8i-r-ccu.h>
+#include <dt-bindings/reset/sun8i-a83t-ccu.h>
 
 / {
 	interrupt-parent = <&gic>;
@@ -175,8 +177,8 @@
 			compatible = "allwinner,sun8i-a83t-dma";
 			reg = <0x01c02000 0x1000>;
 			interrupts = <GIC_SPI 50 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&ccu 21>;
-			resets = <&ccu 7>;
+			clocks = <&ccu CLK_BUS_DMA>;
+			resets = <&ccu RST_BUS_DMA>;
 			#dma-cells = <1>;
 		};
 
@@ -195,7 +197,7 @@
 				     <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
 			reg = <0x01c20800 0x400>;
-			clocks = <&ccu 45>, <&osc24M>, <&osc16Md512>;
+			clocks = <&ccu CLK_BUS_PIO>, <&osc24M>, <&osc16Md512>;
 			clock-names = "apb", "hosc", "losc";
 			gpio-controller;
 			interrupt-controller;
@@ -247,8 +249,8 @@
 				     "allwinner,sun8i-h3-spdif";
 			reg = <0x01c21000 0x400>;
 			interrupts = <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&ccu 44>, <&ccu 76>;
-			resets = <&ccu 32>;
+			clocks = <&ccu CLK_BUS_SPDIF>, <&ccu CLK_SPDIF>;
+			resets = <&ccu RST_BUS_SPDIF>;
 			clock-names = "apb", "spdif";
 			dmas = <&dma 2>;
 			dma-names = "tx";
@@ -263,8 +265,8 @@
 			interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
 			reg-shift = <2>;
 			reg-io-width = <4>;
-			clocks = <&ccu 53>;
-			resets = <&ccu 40>;
+			clocks = <&ccu CLK_BUS_UART0>;
+			resets = <&ccu RST_BUS_UART0>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sunxi-h3-h5.dtsi b/arch/arm/boot/dts/sunxi-h3-h5.dtsi
index 6f2162608006..d38282b9e5d4 100644
--- a/arch/arm/boot/dts/sunxi-h3-h5.dtsi
+++ b/arch/arm/boot/dts/sunxi-h3-h5.dtsi
@@ -394,7 +394,7 @@
 		emac: ethernet@1c30000 {
 			compatible = "allwinner,sun8i-h3-emac";
 			syscon = <&syscon>;
-			reg = <0x01c30000 0x104>;
+			reg = <0x01c30000 0x10000>;
 			interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "macirq";
 			resets = <&ccu RST_BUS_EMAC>;
diff --git a/arch/arm/boot/dts/tango4-vantage-1172.dts b/arch/arm/boot/dts/tango4-vantage-1172.dts
index 86d8df98802f..13bcc460bcb2 100644
--- a/arch/arm/boot/dts/tango4-vantage-1172.dts
+++ b/arch/arm/boot/dts/tango4-vantage-1172.dts
@@ -22,7 +22,7 @@
 };
 
 &eth0 {
-	phy-connection-type = "rgmii";
+	phy-connection-type = "rgmii-id";
 	phy-handle = <&eth0_phy>;
 	#address-cells = <1>;
 	#size-cells = <0>;
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index b5625d009288..e568c8c6f69c 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -1166,7 +1166,7 @@ static struct tvp514x_platform_data tvp5146_pdata = {
 
 #define TVP514X_STD_ALL (V4L2_STD_NTSC | V4L2_STD_PAL)
 
-static const struct vpif_input da850_ch0_inputs[] = {
+static struct vpif_input da850_ch0_inputs[] = {
 	{
 		.input = {
 			.index = 0,
@@ -1181,7 +1181,7 @@ static const struct vpif_input da850_ch0_inputs[] = {
 	},
 };
 
-static const struct vpif_input da850_ch1_inputs[] = {
+static struct vpif_input da850_ch1_inputs[] = {
 	{
 		.input = {
 			.index = 0,
diff --git a/arch/arm/mach-davinci/clock.c b/arch/arm/mach-davinci/clock.c
index f5dce9b4e617..f77a4f766050 100644
--- a/arch/arm/mach-davinci/clock.c
+++ b/arch/arm/mach-davinci/clock.c
@@ -218,6 +218,15 @@ int clk_set_parent(struct clk *clk, struct clk *parent)
 }
 EXPORT_SYMBOL(clk_set_parent);
 
+struct clk *clk_get_parent(struct clk *clk)
+{
+	if (!clk)
+		return NULL;
+
+	return clk->parent;
+}
+EXPORT_SYMBOL(clk_get_parent);
+
 int clk_register(struct clk *clk)
 {
 	if (clk == NULL || IS_ERR(clk))
diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c
index 39ef3b613912..beec5f16443a 100644
--- a/arch/arm/mach-ep93xx/clock.c
+++ b/arch/arm/mach-ep93xx/clock.c
@@ -475,6 +475,26 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 }
 EXPORT_SYMBOL(clk_set_rate);
 
+long clk_round_rate(struct clk *clk, unsigned long rate)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_round_rate);
+
+int clk_set_parent(struct clk *clk, struct clk *parent)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_set_parent);
+
+struct clk *clk_get_parent(struct clk *clk)
+{
+	return clk->parent;
+}
+EXPORT_SYMBOL(clk_get_parent);
+
 
 static char fclk_divisors[] = { 1, 2, 4, 8, 16, 1, 1, 1 };
 static char hclk_divisors[] = { 1, 2, 4, 5, 6, 8, 16, 32 };
diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h
index 7a0c13bf4269..844e8ac593e2 100644
--- a/arch/arm/mach-ixp4xx/include/mach/io.h
+++ b/arch/arm/mach-ixp4xx/include/mach/io.h
@@ -95,8 +95,10 @@ static inline void __indirect_writeb(u8 value, volatile void __iomem *p)
 }
 
 static inline void __indirect_writesb(volatile void __iomem *bus_addr,
-				      const u8 *vaddr, int count)
+				      const void *p, int count)
 {
+	const u8 *vaddr = p;
+
 	while (count--)
 		writeb(*vaddr++, bus_addr);
 }
@@ -118,8 +120,10 @@ static inline void __indirect_writew(u16 value, volatile void __iomem *p)
 }
 
 static inline void __indirect_writesw(volatile void __iomem *bus_addr,
-				      const u16 *vaddr, int count)
+				      const void *p, int count)
 {
+	const u16 *vaddr = p;
+
 	while (count--)
 		writew(*vaddr++, bus_addr);
 }
@@ -137,8 +141,9 @@ static inline void __indirect_writel(u32 value, volatile void __iomem *p)
 }
 
 static inline void __indirect_writesl(volatile void __iomem *bus_addr,
-				      const u32 *vaddr, int count)
+				      const void *p, int count)
 {
+	const u32 *vaddr = p;
 	while (count--)
 		writel(*vaddr++, bus_addr);
 }
@@ -160,8 +165,10 @@ static inline u8 __indirect_readb(const volatile void __iomem *p)
 }
 
 static inline void __indirect_readsb(const volatile void __iomem *bus_addr,
-				     u8 *vaddr, u32 count)
+				     void *p, u32 count)
 {
+	u8 *vaddr = p;
+
 	while (count--)
 		*vaddr++ = readb(bus_addr);
 }
@@ -183,8 +190,10 @@ static inline u16 __indirect_readw(const volatile void __iomem *p)
 }
 
 static inline void __indirect_readsw(const volatile void __iomem *bus_addr,
-				     u16 *vaddr, u32 count)
+				     void *p, u32 count)
 {
+	u16 *vaddr = p;
+
 	while (count--)
 		*vaddr++ = readw(bus_addr);
 }
@@ -204,8 +213,10 @@ static inline u32 __indirect_readl(const volatile void __iomem *p)
 }
 
 static inline void __indirect_readsl(const volatile void __iomem *bus_addr,
-				     u32 *vaddr, u32 count)
+				     void *p, u32 count)
 {
+	u32 *vaddr = p;
+
 	while (count--)
 		*vaddr++ = readl(bus_addr);
 }
@@ -523,8 +534,15 @@ static inline void iowrite32_rep(void __iomem *addr, const void *vaddr,
 #endif
 }
 
-#define	ioport_map(port, nr)		((void __iomem*)(port + PIO_OFFSET))
-#define	ioport_unmap(addr)
+#define ioport_map(port, nr) ioport_map(port, nr)
+static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
+{
+	return ((void __iomem*)((port) + PIO_OFFSET));
+}
+#define	ioport_unmap(addr) ioport_unmap(addr)
+static inline void ioport_unmap(void __iomem *addr)
+{
+}
 #endif /* CONFIG_PCI */
 
 #endif /* __ASM_ARM_ARCH_IO_H */
diff --git a/arch/arm/mach-mmp/devices.c b/arch/arm/mach-mmp/devices.c
index 3330ac7cfbef..671c7a09ab3d 100644
--- a/arch/arm/mach-mmp/devices.c
+++ b/arch/arm/mach-mmp/devices.c
@@ -238,7 +238,7 @@ void pxa_usb_phy_deinit(void __iomem *phy_reg)
 #endif
 
 #if IS_ENABLED(CONFIG_USB_SUPPORT)
-static u64 usb_dma_mask = ~(u32)0;
+static u64 __maybe_unused usb_dma_mask = ~(u32)0;
 
 #if IS_ENABLED(CONFIG_USB_MV_UDC)
 struct resource pxa168_u2o_resources[] = {
diff --git a/arch/arm/mach-mvebu/platsmp.c b/arch/arm/mach-mvebu/platsmp.c
index e62273aacb43..4ffbbd217e82 100644
--- a/arch/arm/mach-mvebu/platsmp.c
+++ b/arch/arm/mach-mvebu/platsmp.c
@@ -211,7 +211,7 @@ static int mv98dx3236_resume_set_cpu_boot_addr(int hw_cpu, void *boot_addr)
 		return PTR_ERR(base);
 
 	writel(0, base + MV98DX3236_CPU_RESUME_CTRL_REG);
-	writel(virt_to_phys(boot_addr), base + MV98DX3236_CPU_RESUME_ADDR_REG);
+	writel(__pa_symbol(boot_addr), base + MV98DX3236_CPU_RESUME_ADDR_REG);
 
 	iounmap(base);
 
diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index 6613a6ff5dbc..6cbc69c92913 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -510,6 +510,7 @@ static void __init ams_delta_init(void)
 static void modem_pm(struct uart_port *port, unsigned int state, unsigned old)
 {
 	struct modem_private_data *priv = port->private_data;
+	int ret;
 
 	if (IS_ERR(priv->regulator))
 		return;
@@ -518,9 +519,16 @@ static void modem_pm(struct uart_port *port, unsigned int state, unsigned old)
 		return;
 
 	if (state == 0)
-		regulator_enable(priv->regulator);
+		ret = regulator_enable(priv->regulator);
 	else if (old == 0)
-		regulator_disable(priv->regulator);
+		ret = regulator_disable(priv->regulator);
+	else
+		ret = 0;
+
+	if (ret)
+		dev_warn(port->dev,
+			 "ams_delta modem_pm: failed to %sable regulator: %d\n",
+			 state ? "dis" : "en", ret);
 }
 
 static struct plat_serial8250_port ams_delta_modem_ports[] = {
diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c
index 4dfb99504810..95ac1929aede 100644
--- a/arch/arm/mach-omap1/board-osk.c
+++ b/arch/arm/mach-omap1/board-osk.c
@@ -441,13 +441,11 @@ static struct spi_board_info __initdata mistral_boardinfo[] = { {
 	.chip_select		= 0,
 } };
 
-#ifdef	CONFIG_PM
 static irqreturn_t
 osk_mistral_wake_interrupt(int irq, void *ignored)
 {
 	return IRQ_HANDLED;
 }
-#endif
 
 static void __init osk_mistral_init(void)
 {
@@ -515,7 +513,6 @@ static void __init osk_mistral_init(void)
 
 		gpio_direction_input(OMAP_MPUIO(2));
 		irq_set_irq_type(irq, IRQ_TYPE_EDGE_RISING);
-#ifdef	CONFIG_PM
 		/* share the IRQ in case someone wants to use the
 		 * button for more than wakeup from system sleep.
 		 */
@@ -529,7 +526,6 @@ static void __init osk_mistral_init(void)
 				ret);
 		} else
 			enable_irq_wake(irq);
-#endif
 	} else
 		printk(KERN_ERR "OSK+Mistral: wakeup button is awol\n");
 
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index dc9e34e670a2..b1e661bb5521 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -28,7 +28,7 @@ static const struct of_device_id omap_dt_match_table[] __initconst = {
 	{ }
 };
 
-static void __init omap_generic_init(void)
+static void __init __maybe_unused omap_generic_init(void)
 {
 	pdata_quirks_init(omap_dt_match_table);
 
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 1d739d1a0a65..1cd20e4d56b0 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -410,7 +410,7 @@ static int _set_hwmod_postsetup_state(struct omap_hwmod *oh, void *data)
 	return omap_hwmod_set_postsetup_state(oh, *(u8 *)data);
 }
 
-static void __init omap_hwmod_init_postsetup(void)
+static void __init __maybe_unused omap_hwmod_init_postsetup(void)
 {
 	u8 postsetup_state;
 
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index d44e0e2f1106..841ba19d64a6 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -486,7 +486,6 @@ int __init omap3_pm_init(void)
 	ret = request_irq(omap_prcm_event_to_irq("io"),
 		_prcm_int_handle_io, IRQF_SHARED | IRQF_NO_SUSPEND, "pm_io",
 		omap3_pm_init);
-	enable_irq(omap_prcm_event_to_irq("io"));
 
 	if (ret) {
 		pr_err("pm: Failed to request pm_io irq\n");
diff --git a/arch/arm/mach-omap2/prm3xxx.c b/arch/arm/mach-omap2/prm3xxx.c
index 382e236fbfd9..64f6451499a7 100644
--- a/arch/arm/mach-omap2/prm3xxx.c
+++ b/arch/arm/mach-omap2/prm3xxx.c
@@ -692,7 +692,6 @@ static int omap3xxx_prm_late_init(void)
 {
 	struct device_node *np;
 	int irq_num;
-	int ret;
 
 	if (!(prm_features & PRM_HAS_IO_WAKEUP))
 		return 0;
@@ -712,12 +711,8 @@ static int omap3xxx_prm_late_init(void)
 	}
 
 	omap3xxx_prm_enable_io_wakeup();
-	ret = omap_prcm_register_chain_handler(&omap3_prcm_irq_setup);
-	if (!ret)
-		irq_set_status_flags(omap_prcm_event_to_irq("io"),
-				     IRQ_NOAUTOEN);
 
-	return ret;
+	return omap_prcm_register_chain_handler(&omap3_prcm_irq_setup);
 }
 
 static void __exit omap3xxx_prm_exit(void)
diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c
index 87e86a4a9ead..3ab5df1ce900 100644
--- a/arch/arm/mach-omap2/prm44xx.c
+++ b/arch/arm/mach-omap2/prm44xx.c
@@ -337,6 +337,27 @@ static void omap44xx_prm_reconfigure_io_chain(void)
 }
 
 /**
+ * omap44xx_prm_enable_io_wakeup - enable wakeup events from I/O wakeup latches
+ *
+ * Activates the I/O wakeup event latches and allows events logged by
+ * those latches to signal a wakeup event to the PRCM.  For I/O wakeups
+ * to occur, WAKEUPENABLE bits must be set in the pad mux registers, and
+ * omap44xx_prm_reconfigure_io_chain() must be called.  No return value.
+ */
+static void __init omap44xx_prm_enable_io_wakeup(void)
+{
+	s32 inst = omap4_prmst_get_prm_dev_inst();
+
+	if (inst == PRM_INSTANCE_UNKNOWN)
+		return;
+
+	omap4_prm_rmw_inst_reg_bits(OMAP4430_GLOBAL_WUEN_MASK,
+				    OMAP4430_GLOBAL_WUEN_MASK,
+				    inst,
+				    omap4_prcm_irq_setup.pm_ctrl);
+}
+
+/**
  * omap44xx_prm_read_reset_sources - return the last SoC reset source
  *
  * Return a u32 representing the last reset sources of the SoC.  The
@@ -668,6 +689,8 @@ struct pwrdm_ops omap4_pwrdm_operations = {
 	.pwrdm_has_voltdm	= omap4_check_vcvp,
 };
 
+static int omap44xx_prm_late_init(void);
+
 /*
  * XXX document
  */
@@ -675,6 +698,7 @@ static struct prm_ll_data omap44xx_prm_ll_data = {
 	.read_reset_sources = &omap44xx_prm_read_reset_sources,
 	.was_any_context_lost_old = &omap44xx_prm_was_any_context_lost_old,
 	.clear_context_loss_flags_old = &omap44xx_prm_clear_context_loss_flags_old,
+	.late_init = &omap44xx_prm_late_init,
 	.assert_hardreset	= omap4_prminst_assert_hardreset,
 	.deassert_hardreset	= omap4_prminst_deassert_hardreset,
 	.is_hardreset_asserted	= omap4_prminst_is_hardreset_asserted,
@@ -711,6 +735,37 @@ int __init omap44xx_prm_init(const struct omap_prcm_init_data *data)
 	return prm_register(&omap44xx_prm_ll_data);
 }
 
+static int omap44xx_prm_late_init(void)
+{
+	int irq_num;
+
+	if (!(prm_features & PRM_HAS_IO_WAKEUP))
+		return 0;
+
+	irq_num = of_irq_get(prm_init_data->np, 0);
+	/*
+	 * Already have OMAP4 IRQ num. For all other platforms, we need
+	 * IRQ numbers from DT
+	 */
+	if (irq_num < 0 && !(prm_init_data->flags & PRM_IRQ_DEFAULT)) {
+		if (irq_num == -EPROBE_DEFER)
+			return irq_num;
+
+		/* Have nothing to do */
+		return 0;
+	}
+
+	/* Once OMAP4 DT is filled as well */
+	if (irq_num >= 0) {
+		omap4_prcm_irq_setup.irq = irq_num;
+		omap4_prcm_irq_setup.xlate_irq = NULL;
+	}
+
+	omap44xx_prm_enable_io_wakeup();
+
+	return omap_prcm_register_chain_handler(&omap4_prcm_irq_setup);
+}
+
 static void __exit omap44xx_prm_exit(void)
 {
 	prm_unregister(&omap44xx_prm_ll_data);
diff --git a/arch/arm/mach-prima2/common.c b/arch/arm/mach-prima2/common.c
index 8cadb302a7d2..ffe05c27087e 100644
--- a/arch/arm/mach-prima2/common.c
+++ b/arch/arm/mach-prima2/common.c
@@ -15,7 +15,7 @@
 #include <linux/of_platform.h>
 #include "common.h"
 
-static void __init sirfsoc_init_late(void)
+static void __init __maybe_unused sirfsoc_init_late(void)
 {
 	sirfsoc_pm_init();
 }
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index 76fbc115ec33..ce7d97babb0f 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -566,6 +566,7 @@ config MACH_ICONTROL
 config ARCH_PXA_ESERIES
 	bool "PXA based Toshiba e-series PDAs"
 	select FB_W100
+	select FB
 	select PXA25x
 
 config MACH_E330
diff --git a/arch/arm/mach-pxa/include/mach/mtd-xip.h b/arch/arm/mach-pxa/include/mach/mtd-xip.h
index 990d2bf2fb45..9bf4ea6a6f74 100644
--- a/arch/arm/mach-pxa/include/mach/mtd-xip.h
+++ b/arch/arm/mach-pxa/include/mach/mtd-xip.h
@@ -17,11 +17,15 @@
 
 #include <mach/regs-ost.h>
 
-#define xip_irqpending()	(ICIP & ICMR)
+/* restored July 2017, this did not build since 2011! */
+
+#define ICIP			io_p2v(0x40d00000)
+#define ICMR			io_p2v(0x40d00004)
+#define xip_irqpending()	(readl(ICIP) & readl(ICMR))
 
 /* we sample OSCR and convert desired delta to usec (1/4 ~= 1000000/3686400) */
-#define xip_currtime()		(OSCR)
-#define xip_elapsed_since(x)	(signed)((OSCR - (x)) / 4)
+#define xip_currtime()		readl(OSCR)
+#define xip_elapsed_since(x)	(signed)((readl(OSCR) - (x)) / 4)
 
 /*
  * xip_cpu_idle() is used when waiting for a delay equal or larger than
diff --git a/arch/arm/mach-rpc/include/mach/hardware.h b/arch/arm/mach-rpc/include/mach/hardware.h
index aa79fa47373a..622d4e5df029 100644
--- a/arch/arm/mach-rpc/include/mach/hardware.h
+++ b/arch/arm/mach-rpc/include/mach/hardware.h
@@ -25,8 +25,8 @@
  *  *_SIZE  is the size of the region
  *  *_BASE  is the virtual address
  */
-#define RAM_SIZE		0x10000000
-#define RAM_START		0x10000000
+#define RPC_RAM_SIZE		0x10000000
+#define RPC_RAM_START		0x10000000
 
 #define EASI_SIZE		0x08000000	/* EASI I/O */
 #define EASI_START		0x08000000
diff --git a/arch/arm/mach-sa1100/clock.c b/arch/arm/mach-sa1100/clock.c
index 0db46895c82a..7d52cd97d96e 100644
--- a/arch/arm/mach-sa1100/clock.c
+++ b/arch/arm/mach-sa1100/clock.c
@@ -35,6 +35,31 @@ struct clk clk_##_name = {				\
 
 static DEFINE_SPINLOCK(clocks_lock);
 
+/* Dummy clk routine to build generic kernel parts that may be using them */
+long clk_round_rate(struct clk *clk, unsigned long rate)
+{
+	return clk_get_rate(clk);
+}
+EXPORT_SYMBOL(clk_round_rate);
+
+int clk_set_rate(struct clk *clk, unsigned long rate)
+{
+	return 0;
+}
+EXPORT_SYMBOL(clk_set_rate);
+
+int clk_set_parent(struct clk *clk, struct clk *parent)
+{
+	return 0;
+}
+EXPORT_SYMBOL(clk_set_parent);
+
+struct clk *clk_get_parent(struct clk *clk)
+{
+	return NULL;
+}
+EXPORT_SYMBOL(clk_get_parent);
+
 static void clk_gpio27_enable(struct clk *clk)
 {
 	/*
diff --git a/arch/arm/mach-sa1100/include/mach/mtd-xip.h b/arch/arm/mach-sa1100/include/mach/mtd-xip.h
index b3d684098fbf..cb76096a2e36 100644
--- a/arch/arm/mach-sa1100/include/mach/mtd-xip.h
+++ b/arch/arm/mach-sa1100/include/mach/mtd-xip.h
@@ -20,7 +20,7 @@
 #define xip_irqpending()	(ICIP & ICMR)
 
 /* we sample OSCR and convert desired delta to usec (1/4 ~= 1000000/3686400) */
-#define xip_currtime()		(OSCR)
-#define xip_elapsed_since(x)	(signed)((OSCR - (x)) / 4)
+#define xip_currtime()		readl_relaxed(OSCR)
+#define xip_elapsed_since(x)	(signed)((readl_relaxed(OSCR) - (x)) / 4)
 
 #endif /* __ARCH_SA1100_MTD_XIP_H__ */
diff --git a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
index 73e3adbc1330..44438f344dc8 100644
--- a/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
+++ b/arch/arm/mach-shmobile/regulator-quirk-rcar-gen2.c
@@ -67,8 +67,12 @@ static int regulator_quirk_notify(struct notifier_block *nb,
 {
 	struct device *dev = data;
 	struct i2c_client *client;
+	static bool done;
 	u32 mon;
 
+	if (done)
+		return 0;
+
 	mon = ioread32(irqc + IRQC_MONITOR);
 	dev_dbg(dev, "%s: %ld, IRQC_MONITOR = 0x%x\n", __func__, action, mon);
 	if (mon & REGULATOR_IRQ_MASK)
@@ -99,7 +103,7 @@ static int regulator_quirk_notify(struct notifier_block *nb,
 remove:
 	dev_info(dev, "IRQ2 is not asserted, removing quirk\n");
 
-	bus_unregister_notifier(&i2c_bus_type, nb);
+	done = true;
 	iounmap(irqc);
 	return 0;
 }
diff --git a/arch/arm/mach-w90x900/clock.c b/arch/arm/mach-w90x900/clock.c
index ac6fd1a2cb59..3f93fac98d97 100644
--- a/arch/arm/mach-w90x900/clock.c
+++ b/arch/arm/mach-w90x900/clock.c
@@ -93,3 +93,32 @@ void nuc900_subclk_enable(struct clk *clk, int enable)
 
 	__raw_writel(clken, W90X900_VA_CLKPWR + SUBCLK);
 }
+
+/* dummy functions, should not be called */
+long clk_round_rate(struct clk *clk, unsigned long rate)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_round_rate);
+
+int clk_set_rate(struct clk *clk, unsigned long rate)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_set_rate);
+
+int clk_set_parent(struct clk *clk, struct clk *parent)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_set_parent);
+
+struct clk *clk_get_parent(struct clk *clk)
+{
+	WARN_ON(clk);
+	return NULL;
+}
+EXPORT_SYMBOL(clk_get_parent);
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
index 9d00622ce845..bd0f33b77f57 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
@@ -452,7 +452,7 @@
 		emac: ethernet@1c30000 {
 			compatible = "allwinner,sun50i-a64-emac";
 			syscon = <&syscon>;
-			reg = <0x01c30000 0x100>;
+			reg = <0x01c30000 0x10000>;
 			interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "macirq";
 			resets = <&ccu RST_BUS_EMAC>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 35b8c88c3220..738ed689ff69 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -400,7 +400,7 @@
 			};
 
 			pwm_AO_ab: pwm@550 {
-				compatible = "amlogic,meson-gx-pwm", "amlogic,meson-gxbb-pwm";
+				compatible = "amlogic,meson-gx-ao-pwm", "amlogic,meson-gxbb-ao-pwm";
 				reg = <0x0 0x00550 0x0 0x10>;
 				#pwm-cells = <3>;
 				status = "disabled";
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts
index 72c5a9f64ca8..94567eb17875 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-khadas-vim.dts
@@ -109,8 +109,8 @@
 	status = "okay";
 	pinctrl-0 = <&pwm_ao_a_3_pins>, <&pwm_ao_b_pins>;
 	pinctrl-names = "default";
-	clocks = <&clkc CLKID_FCLK_DIV4>;
-	clock-names = "clkin0";
+	clocks = <&xtal> , <&xtal>;
+	clock-names = "clkin0", "clkin1" ;
 };
 
 &pwm_ef {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
index 890821d6e52b..266fbcf3e47f 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
@@ -10,12 +10,20 @@
 
 #include <dt-bindings/input/input.h>
 
-#include "meson-gxl-s905x-p212.dtsi"
+#include "meson-gxl-s905x.dtsi"
 
 / {
 	compatible = "libretech,cc", "amlogic,s905x", "amlogic,meson-gxl";
 	model = "Libre Technology CC";
 
+	aliases {
+		serial0 = &uart_AO;
+	};
+
+	chosen {
+		stdout-path = "serial0:115200n8";
+	};
+
 	cvbs-connector {
 		compatible = "composite-video-connector";
 
@@ -26,6 +34,11 @@
 		};
 	};
 
+	emmc_pwrseq: emmc-pwrseq {
+		compatible = "mmc-pwrseq-emmc";
+		reset-gpios = <&gpio BOOT_9 GPIO_ACTIVE_LOW>;
+	};
+
 	hdmi-connector {
 		compatible = "hdmi-connector";
 		type = "a";
@@ -53,6 +66,39 @@
 			linux,default-trigger = "heartbeat";
 		};
 	};
+
+	memory@0 {
+		device_type = "memory";
+		reg = <0x0 0x0 0x0 0x80000000>;
+	};
+
+	vcc_3v3: regulator-vcc_3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "VCC_3V3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	vcc_card: regulator-vcc-card {
+		compatible = "regulator-gpio";
+
+		regulator-name = "VCC_CARD";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <3300000>;
+
+		gpios = <&gpio_ao GPIOAO_3 GPIO_ACTIVE_HIGH>;
+		gpios-states = <0>;
+
+		states = <3300000 0>,
+			 <1800000 1>;
+	};
+
+	vddio_boot: regulator-vddio_boot {
+		compatible = "regulator-fixed";
+		regulator-name = "VDDIO_BOOT";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
 };
 
 &cvbs_vdac_port {
@@ -61,6 +107,16 @@
 	};
 };
 
+&ethmac {
+	status = "okay";
+};
+
+&ir {
+	status = "okay";
+	pinctrl-0 = <&remote_input_ao_pins>;
+	pinctrl-names = "default";
+};
+
 &hdmi_tx {
 	status = "okay";
 	pinctrl-0 = <&hdmi_hpd_pins>, <&hdmi_i2c_pins>;
@@ -73,20 +129,43 @@
 	};
 };
 
-/*
- * The following devices exists but are exposed on the general
- * purpose GPIO header. End user may well decide to use those pins
- * for another purpose
- */
+/* SD card */
+&sd_emmc_b {
+	status = "okay";
+	pinctrl-0 = <&sdcard_pins>;
+	pinctrl-names = "default";
+
+	bus-width = <4>;
+	cap-sd-highspeed;
+	max-frequency = <100000000>;
+	disable-wp;
+
+	cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>;
+	cd-inverted;
 
-&sd_emmc_a {
-	status = "disabled";
+	vmmc-supply = <&vcc_3v3>;
+	vqmmc-supply = <&vcc_card>;
 };
 
-&uart_A {
-	status = "disabled";
+/* eMMC */
+&sd_emmc_c {
+	status = "okay";
+	pinctrl-0 = <&emmc_pins>;
+	pinctrl-names = "default";
+
+	bus-width = <8>;
+	cap-mmc-highspeed;
+	max-frequency = <50000000>;
+	non-removable;
+	disable-wp;
+
+	mmc-pwrseq = <&emmc_pwrseq>;
+	vmmc-supply = <&vcc_3v3>;
+	vqmmc-supply = <&vddio_boot>;
 };
 
-&wifi32k {
-	status = "disabled";
+&uart_AO {
+	status = "okay";
+	pinctrl-0 = <&uart_ao_a_pins>;
+	pinctrl-names = "default";
 };
diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
index dbcc3d4e2ed5..51763d674050 100644
--- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
@@ -219,7 +219,7 @@
 				reg = <0x18800 0x100>, <0x18C00 0x20>;
 				gpiosb: gpio {
 					#gpio-cells = <2>;
-					gpio-ranges = <&pinctrl_sb 0 0 29>;
+					gpio-ranges = <&pinctrl_sb 0 0 30>;
 					gpio-controller;
 					interrupts =
 					<GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
index 726528ce54e9..4c68605675a8 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
@@ -270,6 +270,7 @@
 				interrupt-names = "mem", "ring0", "ring1",
 				"ring2", "ring3", "eip";
 				clocks = <&cpm_clk 1 26>;
+				dma-coherent;
 			};
 		};
 
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
index 95f8e5f607f6..923f354b02f0 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
@@ -64,7 +64,7 @@
 				compatible = "marvell,armada-8k-rtc";
 				reg = <0x284000 0x20>, <0x284080 0x24>;
 				reg-names = "rtc", "rtc-soc";
-				interrupts = <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <ICU_GRP_NSR 77 IRQ_TYPE_LEVEL_HIGH>;
 			};
 
 			cps_ethernet: ethernet@0 {
@@ -261,6 +261,7 @@
 				interrupt-names = "mem", "ring0", "ring1",
 						  "ring2", "ring3", "eip";
 				clocks = <&cps_clk 1 26>;
+				dma-coherent;
 				/*
 				 * The cryptographic engine found on the cp110
 				 * master is enabled by default at the SoC
diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
index aef35e0b685a..a451996f590a 100644
--- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
@@ -508,7 +508,7 @@
 
 	/* audio_clkout0/1/2/3 */
 	#clock-cells = <1>;
-	clock-frequency = <11289600 12288000>;
+	clock-frequency = <12288000 11289600>;
 
 	status = "okay";
 
diff --git a/arch/arm64/boot/dts/renesas/ulcb.dtsi b/arch/arm64/boot/dts/renesas/ulcb.dtsi
index b5c6ee07d7f9..d1a3f3b7a0ab 100644
--- a/arch/arm64/boot/dts/renesas/ulcb.dtsi
+++ b/arch/arm64/boot/dts/renesas/ulcb.dtsi
@@ -281,7 +281,7 @@
 
 	/* audio_clkout0/1/2/3 */
 	#clock-cells = <1>;
-	clock-frequency = <11289600 12288000>;
+	clock-frequency = <12288000 11289600>;
 
 	status = "okay";
 
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 6c7d147eed54..b4ca115b3be1 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -476,6 +476,7 @@ CONFIG_QCOM_CLK_SMD_RPM=y
 CONFIG_MSM_GCC_8916=y
 CONFIG_MSM_GCC_8994=y
 CONFIG_MSM_MMCC_8996=y
+CONFIG_HWSPINLOCK=y
 CONFIG_HWSPINLOCK_QCOM=y
 CONFIG_ARM_MHU=y
 CONFIG_PLATFORM_MHU=y
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 32f82723338a..ef39dcb9ca6a 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -64,8 +64,10 @@
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
  */
 #define VA_BITS			(CONFIG_ARM64_VA_BITS)
-#define VA_START		(UL(0xffffffffffffffff) << VA_BITS)
-#define PAGE_OFFSET		(UL(0xffffffffffffffff) << (VA_BITS - 1))
+#define VA_START		(UL(0xffffffffffffffff) - \
+	(UL(1) << VA_BITS) + 1)
+#define PAGE_OFFSET		(UL(0xffffffffffffffff) - \
+	(UL(1) << (VA_BITS - 1)) + 1)
 #define KIMAGE_VADDR		(MODULES_END)
 #define MODULES_END		(MODULES_VADDR + MODULES_VSIZE)
 #define MODULES_VADDR		(VA_START + KASAN_SHADOW_SIZE)
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index d48f47080213..8a62648848e5 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -523,7 +523,7 @@ static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
 {
 	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
 
-	pt_regs_write_reg(regs, rt, read_sysreg(cntfrq_el0));
+	pt_regs_write_reg(regs, rt, arch_timer_get_rate());
 	regs->pc += 4;
 }
 
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 77862881ae86..2e070d3baf9f 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -764,7 +764,7 @@ static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	if (p->is_write) {
 		if (r->CRm & 0x2)
 			/* accessing PMOVSSET_EL0 */
-			kvm_pmu_overflow_set(vcpu, p->regval & mask);
+			vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= (p->regval & mask);
 		else
 			/* accessing PMOVSCLR_EL0 */
 			vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index c7861c9864e6..2509e4fe6992 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -163,26 +163,27 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	/* only preserve the access flags and write permission */
 	pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
 
-	/*
-	 * PTE_RDONLY is cleared by default in the asm below, so set it in
-	 * back if necessary (read-only or clean PTE).
-	 */
+	/* set PTE_RDONLY if actual read-only or clean PTE */
 	if (!pte_write(entry) || !pte_sw_dirty(entry))
 		pte_val(entry) |= PTE_RDONLY;
 
 	/*
 	 * Setting the flags must be done atomically to avoid racing with the
-	 * hardware update of the access/dirty state.
+	 * hardware update of the access/dirty state. The PTE_RDONLY bit must
+	 * be set to the most permissive (lowest value) of *ptep and entry
+	 * (calculated as: a & b == ~(~a | ~b)).
 	 */
+	pte_val(entry) ^= PTE_RDONLY;
 	asm volatile("//	ptep_set_access_flags\n"
 	"	prfm	pstl1strm, %2\n"
 	"1:	ldxr	%0, %2\n"
-	"	and	%0, %0, %3		// clear PTE_RDONLY\n"
+	"	eor	%0, %0, %3		// negate PTE_RDONLY in *ptep\n"
 	"	orr	%0, %0, %4		// set flags\n"
+	"	eor	%0, %0, %3		// negate final PTE_RDONLY\n"
 	"	stxr	%w1, %0, %2\n"
 	"	cbnz	%w1, 1b\n"
 	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
-	: "L" (~PTE_RDONLY), "r" (pte_val(entry)));
+	: "L" (PTE_RDONLY), "r" (pte_val(entry)));
 
 	flush_tlb_fix_spurious_fault(vma, address);
 	return 1;
diff --git a/arch/mips/include/asm/mach-ralink/ralink_regs.h b/arch/mips/include/asm/mach-ralink/ralink_regs.h
index 9df1a53bcb36..b4e7dfa214eb 100644
--- a/arch/mips/include/asm/mach-ralink/ralink_regs.h
+++ b/arch/mips/include/asm/mach-ralink/ralink_regs.h
@@ -13,6 +13,8 @@
 #ifndef _RALINK_REGS_H_
 #define _RALINK_REGS_H_
 
+#include <linux/io.h>
+
 enum ralink_soc_type {
 	RALINK_UNKNOWN = 0,
 	RT2880_SOC,
diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c
index 094a0ee4af46..9be8b08ae46b 100644
--- a/arch/mips/ralink/mt7620.c
+++ b/arch/mips/ralink/mt7620.c
@@ -12,6 +12,7 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/bug.h>
 
 #include <asm/mipsregs.h>
 #include <asm/mach-ralink/ralink_regs.h>
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 531da9eb8f43..dda1f558ef35 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -47,6 +47,9 @@ config PARISC
 	  and later HP3000 series).  The PA-RISC Linux project home page is
 	  at <http://www.parisc-linux.org/>.
 
+config CPU_BIG_ENDIAN
+	def_bool y
+
 config MMU
 	def_bool y
 
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index 88fe0aad4390..bc208136bbb2 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -34,7 +34,7 @@ struct thread_info {
 
 /* thread information allocation */
 
-#define THREAD_SIZE_ORDER	2 /* PA-RISC requires at least 16k stack */
+#define THREAD_SIZE_ORDER	3 /* PA-RISC requires at least 32k stack */
 /* Be sure to hunt all references to this down when you change the size of
  * the kernel stack */
 #define THREAD_SIZE             (PAGE_SIZE << THREAD_SIZE_ORDER)
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 85a92db70afc..19c0c141bc3f 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -587,13 +587,12 @@ void flush_cache_range(struct vm_area_struct *vma,
 	if (parisc_requires_coherency())
 		flush_tlb_range(vma, start, end);
 
-	if ((end - start) >= parisc_cache_flush_threshold) {
+	if ((end - start) >= parisc_cache_flush_threshold
+	    || vma->vm_mm->context != mfsp(3)) {
 		flush_cache_all();
 		return;
 	}
 
-	BUG_ON(vma->vm_mm->context != mfsp(3));
-
 	flush_user_dcache_range_asm(start, end);
 	if (vma->vm_flags & VM_EXEC)
 		flush_user_icache_range_asm(start, end);
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index 5404e4086cb9..0ca254085a66 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -380,7 +380,7 @@ static inline int eirr_to_irq(unsigned long eirr)
 /*
  * IRQ STACK - used for irq handler
  */
-#define IRQ_STACK_SIZE      (4096 << 2) /* 16k irq stack size */
+#define IRQ_STACK_SIZE      (4096 << 3) /* 32k irq stack size */
 
 union irq_stack_union {
 	unsigned long stack[IRQ_STACK_SIZE/sizeof(unsigned long)];
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index a7814a7b1523..6f952fe1f084 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -25,12 +25,20 @@ compress-$(CONFIG_KERNEL_XZ)   := CONFIG_KERNEL_XZ
 BOOTCFLAGS    := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		 -fno-strict-aliasing -Os -msoft-float -pipe \
 		 -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
-		 -isystem $(shell $(CROSS32CC) -print-file-name=include) \
 		 -D$(compress-y)
 
+BOOTCC := $(CC)
 ifdef CONFIG_PPC64_BOOT_WRAPPER
 BOOTCFLAGS	+= -m64
+else
+BOOTCFLAGS	+= -m32
+ifdef CROSS32_COMPILE
+    BOOTCC := $(CROSS32_COMPILE)gcc
+endif
 endif
+
+BOOTCFLAGS	+= -isystem $(shell $(BOOTCC) -print-file-name=include)
+
 ifdef CONFIG_CPU_BIG_ENDIAN
 BOOTCFLAGS	+= -mbig-endian
 else
@@ -183,10 +191,10 @@ clean-files := $(zlib-) $(zlibheader-) $(zliblinuxheader-) \
 		empty.c zImage.coff.lds zImage.ps3.lds zImage.lds
 
 quiet_cmd_bootcc = BOOTCC  $@
-      cmd_bootcc = $(CROSS32CC) -Wp,-MD,$(depfile) $(BOOTCFLAGS) -c -o $@ $<
+      cmd_bootcc = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTCFLAGS) -c -o $@ $<
 
 quiet_cmd_bootas = BOOTAS  $@
-      cmd_bootas = $(CROSS32CC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $<
+      cmd_bootas = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $<
 
 quiet_cmd_bootar = BOOTAR  $@
       cmd_bootar = $(CROSS32AR) -cr$(KBUILD_ARFLAGS) $@.$$$$ $(filter-out FORCE,$^); mv $@.$$$$ $@
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index d1da415e283c..818a58fc3f4f 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -608,9 +608,17 @@ static inline pte_t pte_mkdevmap(pte_t pte)
 	return __pte(pte_val(pte) | _PAGE_SPECIAL|_PAGE_DEVMAP);
 }
 
+/*
+ * This is potentially called with a pmd as the argument, in which case it's not
+ * safe to check _PAGE_DEVMAP unless we also confirm that _PAGE_PTE is set.
+ * That's because the bit we use for _PAGE_DEVMAP is not reserved for software
+ * use in page directory entries (ie. non-ptes).
+ */
 static inline int pte_devmap(pte_t pte)
 {
-	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DEVMAP));
+	u64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE);
+
+	return (pte_raw(pte) & mask) == mask;
 }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 9029afd1fa2a..f14f3c04ec7e 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1325,10 +1325,18 @@ EXC_VIRT_NONE(0x5800, 0x100)
 	std	r10,PACA_EXGEN+EX_R13(r13);		\
 	EXCEPTION_PROLOG_PSERIES_1(soft_nmi_common, _H)
 
+/*
+ * Branch to soft_nmi_interrupt using the emergency stack. The emergency
+ * stack is one that is usable by maskable interrupts so long as MSR_EE
+ * remains off. It is used for recovery when something has corrupted the
+ * normal kernel stack, for example. The "soft NMI" must not use the process
+ * stack because we want irq disabled sections to avoid touching the stack
+ * at all (other than PMU interrupts), so use the emergency stack for this,
+ * and run it entirely with interrupts hard disabled.
+ */
 EXC_COMMON_BEGIN(soft_nmi_common)
 	mr	r10,r1
 	ld	r1,PACAEMERGSP(r13)
-	ld	r1,PACA_NMI_EMERG_SP(r13)
 	subi	r1,r1,INT_FRAME_SIZE
 	EXCEPTION_COMMON_NORET_STACK(PACA_EXGEN, 0x900,
 			system_reset, soft_nmi_interrupt,
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 516ebef905c0..e6252c5a57a4 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -460,11 +460,17 @@ pnv_restore_hyp_resource_arch300:
 	/*
 	 * Workaround for POWER9, if we lost resources, the ERAT
 	 * might have been mixed up and needs flushing. We also need
-	 * to reload MMCR0 (see comment above).
+	 * to reload MMCR0 (see comment above). We also need to set
+	 * then clear bit 60 in MMCRA to ensure the PMU starts running.
 	 */
 	blt	cr3,1f
 	PPC_INVALIDATE_ERAT
 	ld	r1,PACAR1(r13)
+	mfspr	r4,SPRN_MMCRA
+	ori	r4,r4,(1 << (63-60))
+	mtspr	SPRN_MMCRA,r4
+	xori	r4,r4,(1 << (63-60))
+	mtspr	SPRN_MMCRA,r4
 	ld	r4,_MMCR0(r1)
 	mtspr	SPRN_MMCR0,r4
 1:
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 0bcec745a672..f291f7826abc 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -145,6 +145,19 @@ notrace unsigned int __check_irq_replay(void)
 
 	/* Clear bit 0 which we wouldn't clear otherwise */
 	local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+	if (happened & PACA_IRQ_HARD_DIS) {
+		/*
+		 * We may have missed a decrementer interrupt if hard disabled.
+		 * Check the decrementer register in case we had a rollover
+		 * while hard disabled.
+		 */
+		if (!(happened & PACA_IRQ_DEC)) {
+			if (decrementer_check_overflow()) {
+				local_paca->irq_happened |= PACA_IRQ_DEC;
+				happened |= PACA_IRQ_DEC;
+			}
+		}
+	}
 
 	/*
 	 * Force the delivery of pending soft-disabled interrupts on PS3.
@@ -170,7 +183,7 @@ notrace unsigned int __check_irq_replay(void)
 	 * in case we also had a rollover while hard disabled
 	 */
 	local_paca->irq_happened &= ~PACA_IRQ_DEC;
-	if ((happened & PACA_IRQ_DEC) || decrementer_check_overflow())
+	if (happened & PACA_IRQ_DEC)
 		return 0x900;
 
 	/* Finally check if an external interrupt happened */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 925a4ef90559..660ed39e9c9a 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -127,12 +127,19 @@ static void flush_tmregs_to_thread(struct task_struct *tsk)
 	 * If task is not current, it will have been flushed already to
 	 * it's thread_struct during __switch_to().
 	 *
-	 * A reclaim flushes ALL the state.
+	 * A reclaim flushes ALL the state or if not in TM save TM SPRs
+	 * in the appropriate thread structures from live.
 	 */
 
-	if (tsk == current && MSR_TM_SUSPENDED(mfmsr()))
-		tm_reclaim_current(TM_CAUSE_SIGNAL);
+	if (tsk != current)
+		return;
 
+	if (MSR_TM_SUSPENDED(mfmsr())) {
+		tm_reclaim_current(TM_CAUSE_SIGNAL);
+	} else {
+		tm_enable();
+		tm_save_sprs(&(tsk->thread));
+	}
 }
 #else
 static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 997c88d54acf..cf0e1245b8cc 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1003,21 +1003,13 @@ static struct sched_domain_topology_level powerpc_topology[] = {
 	{ NULL, },
 };
 
-static __init long smp_setup_cpu_workfn(void *data __always_unused)
-{
-	smp_ops->setup_cpu(boot_cpuid);
-	return 0;
-}
-
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	/*
-	 * We want the setup_cpu() here to be called on the boot CPU, but
-	 * init might run on any CPU, so make sure it's invoked on the boot
-	 * CPU.
+	 * We are running pinned to the boot CPU, see rest_init().
 	 */
 	if (smp_ops && smp_ops->setup_cpu)
-		work_on_cpu_safe(boot_cpuid, smp_setup_cpu_workfn, NULL);
+		smp_ops->setup_cpu(boot_cpuid);
 
 	if (smp_ops && smp_ops->bringup_done)
 		smp_ops->bringup_done();
diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
index d7c9b186954d..763ffca9628d 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
@@ -89,7 +89,7 @@ static int __init of_fsl_spi_probe(char *type, char *compatible, u32 sysclk,
 			goto err;
 
 		ret = of_irq_to_resource(np, 0, &res[1]);
-		if (!ret)
+		if (ret <= 0)
 			goto err;
 
 		pdev = platform_device_alloc("mpc83xx_spi", i);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 437613588df1..b900eb1d5e17 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1852,6 +1852,14 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
 			/* 4GB offset bypasses 32-bit space */
 			set_dma_offset(&pdev->dev, (1ULL << 32));
 			set_dma_ops(&pdev->dev, &dma_direct_ops);
+		} else if (dma_mask >> 32 && dma_mask != DMA_BIT_MASK(64)) {
+			/*
+			 * Fail the request if a DMA mask between 32 and 64 bits
+			 * was requested but couldn't be fulfilled. Ideally we
+			 * would do this for 64-bits but historically we have
+			 * always fallen back to 32-bits.
+			 */
+			return -ENOMEM;
 		} else {
 			dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
 			set_dma_ops(&pdev->dev, &dma_iommu_ops);
diff --git a/arch/sparc/configs/sparc32_defconfig b/arch/sparc/configs/sparc32_defconfig
index c74d3701ad68..207a43a2d8b3 100644
--- a/arch/sparc/configs/sparc32_defconfig
+++ b/arch/sparc/configs/sparc32_defconfig
@@ -1,4 +1,3 @@
-CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_LOG_BUF_SHIFT=14
@@ -23,7 +22,6 @@ CONFIG_IP_PNP_DHCP=y
 CONFIG_INET_AH=y
 CONFIG_INET_ESP=y
 CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
@@ -69,7 +67,6 @@ CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
 CONFIG_EXT2_FS_SECURITY=y
-CONFIG_AUTOFS_FS=m
 CONFIG_AUTOFS4_FS=m
 CONFIG_ISO9660_FS=m
 CONFIG_PROC_KCORE=y
@@ -82,7 +79,6 @@ CONFIG_NLS=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_HUNG_TASK=y
 # CONFIG_SCHED_DEBUG is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_KGDB=y
 CONFIG_KGDB_TESTS=y
 CONFIG_CRYPTO_NULL=m
diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig
index b2e650d1764f..ca8609d7292f 100644
--- a/arch/sparc/configs/sparc64_defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
@@ -1,5 +1,4 @@
 CONFIG_64BIT=y
-CONFIG_EXPERIMENTAL=y
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
@@ -184,7 +183,6 @@ CONFIG_HID_TOPSEED=y
 CONFIG_HID_THRUSTMASTER=y
 CONFIG_HID_ZEROPLUS=y
 CONFIG_USB=y
-# CONFIG_USB_DEVICE_CLASS is not set
 CONFIG_USB_EHCI_HCD=m
 # CONFIG_USB_EHCI_TT_NEWSCHED is not set
 CONFIG_USB_OHCI_HCD=y
@@ -210,8 +208,6 @@ CONFIG_LOCKUP_DETECTOR=y
 CONFIG_DETECT_HUNG_TASK=y
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_SCHEDSTATS=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_UPROBE_EVENTS=y
 CONFIG_KEYS=y
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index 2cddcda4f85f..87841d687f8d 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -27,9 +27,11 @@ void destroy_context(struct mm_struct *mm);
 void __tsb_context_switch(unsigned long pgd_pa,
 			  struct tsb_config *tsb_base,
 			  struct tsb_config *tsb_huge,
-			  unsigned long tsb_descr_pa);
+			  unsigned long tsb_descr_pa,
+			  unsigned long secondary_ctx);
 
-static inline void tsb_context_switch(struct mm_struct *mm)
+static inline void tsb_context_switch_ctx(struct mm_struct *mm,
+					  unsigned long ctx)
 {
 	__tsb_context_switch(__pa(mm->pgd),
 			     &mm->context.tsb_block[MM_TSB_BASE],
@@ -40,9 +42,12 @@ static inline void tsb_context_switch(struct mm_struct *mm)
 #else
 			     NULL
 #endif
-			     , __pa(&mm->context.tsb_descr[MM_TSB_BASE]));
+			     , __pa(&mm->context.tsb_descr[MM_TSB_BASE]),
+			     ctx);
 }
 
+#define tsb_context_switch(X) tsb_context_switch_ctx(X, 0)
+
 void tsb_grow(struct mm_struct *mm,
 	      unsigned long tsb_index,
 	      unsigned long mm_rss);
@@ -112,8 +117,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 	 * cpu0 to update it's TSB because at that point the cpu_vm_mask
 	 * only had cpu1 set in it.
 	 */
-	load_secondary_context(mm);
-	tsb_context_switch(mm);
+	tsb_context_switch_ctx(mm, CTX_HWBITS(mm->context));
 
 	/* Any time a processor runs a context on an address space
 	 * for the first time, we must flush that context out of the
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index 07c0df924960..db872dbfafe9 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -360,6 +360,7 @@ tsb_flush:
 	 * %o1:	TSB base config pointer
 	 * %o2:	TSB huge config pointer, or NULL if none
 	 * %o3:	Hypervisor TSB descriptor physical address
+	 * %o4: Secondary context to load, if non-zero
 	 *
 	 * We have to run this whole thing with interrupts
 	 * disabled so that the current cpu doesn't change
@@ -372,6 +373,17 @@ __tsb_context_switch:
 	rdpr	%pstate, %g1
 	wrpr	%g1, PSTATE_IE, %pstate
 
+	brz,pn	%o4, 1f
+	 mov	SECONDARY_CONTEXT, %o5
+
+661:	stxa	%o4, [%o5] ASI_DMMU
+	.section .sun4v_1insn_patch, "ax"
+	.word	661b
+	stxa	%o4, [%o5] ASI_MMU
+	.previous
+	flush	%g6
+
+1:
 	TRAP_LOAD_TRAP_BLOCK(%g2, %g3)
 
 	stx	%o0, [%g2 + TRAP_PER_CPU_PGD_PADDR]
diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S
index 54f98706b03b..5a8cb37f0a3b 100644
--- a/arch/sparc/lib/U3memcpy.S
+++ b/arch/sparc/lib/U3memcpy.S
@@ -145,13 +145,13 @@ ENDPROC(U3_retl_o2_plus_GS_plus_0x08)
 ENTRY(U3_retl_o2_and_7_plus_GS)
 	and	%o2, 7, %o2
 	retl
-	 add	%o2, GLOBAL_SPARE, %o2
+	 add	%o2, GLOBAL_SPARE, %o0
 ENDPROC(U3_retl_o2_and_7_plus_GS)
 ENTRY(U3_retl_o2_and_7_plus_GS_plus_8)
 	add	GLOBAL_SPARE, 8, GLOBAL_SPARE
 	and	%o2, 7, %o2
 	retl
-	 add	%o2, GLOBAL_SPARE, %o2
+	 add	%o2, GLOBAL_SPARE, %o0
 ENDPROC(U3_retl_o2_and_7_plus_GS_plus_8)
 #endif
 
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 3c40ebd50f92..fed73f14aa49 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -325,6 +325,29 @@ static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_inde
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
+static void __init add_huge_page_size(unsigned long size)
+{
+	unsigned int order;
+
+	if (size_to_hstate(size))
+		return;
+
+	order = ilog2(size) - PAGE_SHIFT;
+	hugetlb_add_hstate(order);
+}
+
+static int __init hugetlbpage_init(void)
+{
+	add_huge_page_size(1UL << HPAGE_64K_SHIFT);
+	add_huge_page_size(1UL << HPAGE_SHIFT);
+	add_huge_page_size(1UL << HPAGE_256MB_SHIFT);
+	add_huge_page_size(1UL << HPAGE_2GB_SHIFT);
+
+	return 0;
+}
+
+arch_initcall(hugetlbpage_init);
+
 static int __init setup_hugepagesz(char *string)
 {
 	unsigned long long hugepage_size;
@@ -364,7 +387,7 @@ static int __init setup_hugepagesz(char *string)
 		goto out;
 	}
 
-	hugetlb_add_hstate(hugepage_shift - PAGE_SHIFT);
+	add_huge_page_size(hugepage_size);
 	rc = 1;
 
 out:
diff --git a/arch/sparc/power/hibernate.c b/arch/sparc/power/hibernate.c
index 17bd2e167e07..df707a8ad311 100644
--- a/arch/sparc/power/hibernate.c
+++ b/arch/sparc/power/hibernate.c
@@ -35,6 +35,5 @@ void restore_processor_state(void)
 {
 	struct mm_struct *mm = current->active_mm;
 
-	load_secondary_context(mm);
-	tsb_context_switch(mm);
+	tsb_context_switch_ctx(mm, CTX_HWBITS(mm->context));
 }
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index d869c8671e36..7cf7c70b6ef2 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -8,20 +8,25 @@
  * This file is licensed under GPLv2.
  */
 
-#include <linux/jiffies.h>
+#include <linux/delay.h>
+#include <linux/ktime.h>
 #include <linux/math64.h>
 #include <linux/percpu.h>
 #include <linux/smp.h>
 
 struct aperfmperf_sample {
 	unsigned int	khz;
-	unsigned long	jiffies;
+	ktime_t	time;
 	u64	aperf;
 	u64	mperf;
 };
 
 static DEFINE_PER_CPU(struct aperfmperf_sample, samples);
 
+#define APERFMPERF_CACHE_THRESHOLD_MS	10
+#define APERFMPERF_REFRESH_DELAY_MS	20
+#define APERFMPERF_STALE_THRESHOLD_MS	1000
+
 /*
  * aperfmperf_snapshot_khz()
  * On the current CPU, snapshot APERF, MPERF, and jiffies
@@ -33,9 +38,11 @@ static void aperfmperf_snapshot_khz(void *dummy)
 	u64 aperf, aperf_delta;
 	u64 mperf, mperf_delta;
 	struct aperfmperf_sample *s = this_cpu_ptr(&samples);
+	ktime_t now = ktime_get();
+	s64 time_delta = ktime_ms_delta(now, s->time);
 
-	/* Don't bother re-computing within 10 ms */
-	if (time_before(jiffies, s->jiffies + HZ/100))
+	/* Don't bother re-computing within the cache threshold time. */
+	if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS)
 		return;
 
 	rdmsrl(MSR_IA32_APERF, aperf);
@@ -51,22 +58,21 @@ static void aperfmperf_snapshot_khz(void *dummy)
 	if (mperf_delta == 0)
 		return;
 
-	/*
-	 * if (cpu_khz * aperf_delta) fits into ULLONG_MAX, then
-	 *	khz = (cpu_khz * aperf_delta) / mperf_delta
-	 */
-	if (div64_u64(ULLONG_MAX, cpu_khz) > aperf_delta)
-		s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
-	else	/* khz = aperf_delta / (mperf_delta / cpu_khz) */
-		s->khz = div64_u64(aperf_delta,
-			div64_u64(mperf_delta, cpu_khz));
-	s->jiffies = jiffies;
+	s->time = now;
 	s->aperf = aperf;
 	s->mperf = mperf;
+
+	/* If the previous iteration was too long ago, discard it. */
+	if (time_delta > APERFMPERF_STALE_THRESHOLD_MS)
+		s->khz = 0;
+	else
+		s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
 }
 
 unsigned int arch_freq_get_on_cpu(int cpu)
 {
+	unsigned int khz;
+
 	if (!cpu_khz)
 		return 0;
 
@@ -74,6 +80,12 @@ unsigned int arch_freq_get_on_cpu(int cpu)
 		return 0;
 
 	smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
+	khz = per_cpu(samples.khz, cpu);
+	if (khz)
+		return khz;
+
+	msleep(APERFMPERF_REFRESH_DELAY_MS);
+	smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1);
 
 	return per_cpu(samples.khz, cpu);
 }
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 16f82a3aaec7..8ce4212e2b8d 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -345,21 +345,10 @@ static int hpet_shutdown(struct clock_event_device *evt, int timer)
 	return 0;
 }
 
-static int hpet_resume(struct clock_event_device *evt, int timer)
-{
-	if (!timer) {
-		hpet_enable_legacy_int();
-	} else {
-		struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-
-		irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
-		irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
-		disable_hardirq(hdev->irq);
-		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
-		enable_irq(hdev->irq);
-	}
+static int hpet_resume(struct clock_event_device *evt)
+{
+	hpet_enable_legacy_int();
 	hpet_print_config();
-
 	return 0;
 }
 
@@ -417,7 +406,7 @@ static int hpet_legacy_set_periodic(struct clock_event_device *evt)
 
 static int hpet_legacy_resume(struct clock_event_device *evt)
 {
-	return hpet_resume(evt, 0);
+	return hpet_resume(evt);
 }
 
 static int hpet_legacy_next_event(unsigned long delta,
@@ -510,8 +499,14 @@ static int hpet_msi_set_periodic(struct clock_event_device *evt)
 static int hpet_msi_resume(struct clock_event_device *evt)
 {
 	struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
+	struct irq_data *data = irq_get_irq_data(hdev->irq);
+	struct msi_msg msg;
 
-	return hpet_resume(evt, hdev->num);
+	/* Restore the MSI msg and unmask the interrupt */
+	irq_chip_compose_msi_msg(data, &msg);
+	hpet_msi_write(hdev, &msg);
+	hpet_msi_unmask(data);
+	return 0;
 }
 
 static int hpet_msi_next_event(unsigned long delta,
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 71c17a5be983..d04e30e3c0ff 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -151,6 +151,8 @@ void kvm_async_pf_task_wait(u32 token)
 		if (hlist_unhashed(&n.link))
 			break;
 
+		rcu_irq_exit();
+
 		if (!n.halted) {
 			local_irq_enable();
 			schedule();
@@ -159,11 +161,11 @@ void kvm_async_pf_task_wait(u32 token)
 			/*
 			 * We cannot reschedule. So halt.
 			 */
-			rcu_irq_exit();
 			native_safe_halt();
 			local_irq_disable();
-			rcu_irq_enter();
 		}
+
+		rcu_irq_enter();
 	}
 	if (!n.halted)
 		finish_swait(&n.wq, &wait);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 4d8141e533c3..1107626938cc 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2430,6 +2430,16 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 	svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
 	svm->vmcb->control.exit_code_hi = 0;
 	svm->vmcb->control.exit_info_1 = error_code;
+
+	/*
+	 * FIXME: we should not write CR2 when L1 intercepts an L2 #PF exception.
+	 * The fix is to add the ancillary datum (CR2 or DR6) to structs
+	 * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6 can be
+	 * written only when inject_pending_event runs (DR6 would written here
+	 * too).  This should be conditional on a new capability---if the
+	 * capability is disabled, kvm_multiple_exception would write the
+	 * ancillary information to CR2 or DR6, for backwards ABI-compatibility.
+	 */
 	if (svm->vcpu.arch.exception.nested_apf)
 		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token;
 	else
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 39a6222bf968..9b21b1223035 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -416,13 +416,10 @@ struct nested_vmx {
 
 	/* The guest-physical address of the current VMCS L1 keeps for L2 */
 	gpa_t current_vmptr;
-	/* The host-usable pointer to the above */
-	struct page *current_vmcs12_page;
-	struct vmcs12 *current_vmcs12;
 	/*
 	 * Cache of the guest's VMCS, existing outside of guest memory.
 	 * Loaded from guest memory during VMPTRLD. Flushed to guest
-	 * memory during VMXOFF, VMCLEAR, VMPTRLD.
+	 * memory during VMCLEAR and VMPTRLD.
 	 */
 	struct vmcs12 *cached_vmcs12;
 	/*
@@ -927,6 +924,10 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var);
 static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
 static int alloc_identity_pagetable(struct kvm *kvm);
+static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
+static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
+static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
+					    u16 error_code);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -2428,6 +2429,30 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	vmx_set_interrupt_shadow(vcpu, 0);
 }
 
+static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
+					       unsigned long exit_qual)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned int nr = vcpu->arch.exception.nr;
+	u32 intr_info = nr | INTR_INFO_VALID_MASK;
+
+	if (vcpu->arch.exception.has_error_code) {
+		vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code;
+		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
+	}
+
+	if (kvm_exception_is_soft(nr))
+		intr_info |= INTR_TYPE_SOFT_EXCEPTION;
+	else
+		intr_info |= INTR_TYPE_HARD_EXCEPTION;
+
+	if (!(vmcs12->idt_vectoring_info_field & VECTORING_INFO_VALID_MASK) &&
+	    vmx_get_nmi_mask(vcpu))
+		intr_info |= INTR_INFO_UNBLOCK_NMI;
+
+	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
+}
+
 /*
  * KVM wants to inject page-faults which it got to the guest. This function
  * checks whether in a nested guest, we need to inject them to L1 or L2.
@@ -2437,23 +2462,38 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	unsigned int nr = vcpu->arch.exception.nr;
 
-	if (!((vmcs12->exception_bitmap & (1u << nr)) ||
-		(nr == PF_VECTOR && vcpu->arch.exception.nested_apf)))
-		return 0;
+	if (nr == PF_VECTOR) {
+		if (vcpu->arch.exception.nested_apf) {
+			nested_vmx_inject_exception_vmexit(vcpu,
+							   vcpu->arch.apf.nested_apf_token);
+			return 1;
+		}
+		/*
+		 * FIXME: we must not write CR2 when L1 intercepts an L2 #PF exception.
+		 * The fix is to add the ancillary datum (CR2 or DR6) to structs
+		 * kvm_queued_exception and kvm_vcpu_events, so that CR2 and DR6
+		 * can be written only when inject_pending_event runs.  This should be
+		 * conditional on a new capability---if the capability is disabled,
+		 * kvm_multiple_exception would write the ancillary information to
+		 * CR2 or DR6, for backwards ABI-compatibility.
+		 */
+		if (nested_vmx_is_page_fault_vmexit(vmcs12,
+						    vcpu->arch.exception.error_code)) {
+			nested_vmx_inject_exception_vmexit(vcpu, vcpu->arch.cr2);
+			return 1;
+		}
+	} else {
+		unsigned long exit_qual = 0;
+		if (nr == DB_VECTOR)
+			exit_qual = vcpu->arch.dr6;
 
-	if (vcpu->arch.exception.nested_apf) {
-		vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code);
-		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
-			PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
-			INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
-			vcpu->arch.apf.nested_apf_token);
-		return 1;
+		if (vmcs12->exception_bitmap & (1u << nr)) {
+			nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+			return 1;
+		}
 	}
 
-	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
-			  vmcs_read32(VM_EXIT_INTR_INFO),
-			  vmcs_readl(EXIT_QUALIFICATION));
-	return 1;
+	return 0;
 }
 
 static void vmx_queue_exception(struct kvm_vcpu *vcpu)
@@ -2667,7 +2707,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	 * reason is that if one of these bits is necessary, it will appear
 	 * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control
 	 * fields of vmcs01 and vmcs02, will turn these bits off - and
-	 * nested_vmx_exit_handled() will not pass related exits to L1.
+	 * nested_vmx_exit_reflected() will not pass related exits to L1.
 	 * These rules have exceptions below.
 	 */
 
@@ -4955,6 +4995,28 @@ static bool vmx_get_enable_apicv(void)
 	return enable_apicv;
 }
 
+static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	gfn_t gfn;
+
+	/*
+	 * Don't need to mark the APIC access page dirty; it is never
+	 * written to by the CPU during APIC virtualization.
+	 */
+
+	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+		gfn = vmcs12->virtual_apic_page_addr >> PAGE_SHIFT;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+	}
+
+	if (nested_cpu_has_posted_intr(vmcs12)) {
+		gfn = vmcs12->posted_intr_desc_addr >> PAGE_SHIFT;
+		kvm_vcpu_mark_page_dirty(vcpu, gfn);
+	}
+}
+
+
 static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -4962,18 +5024,15 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	void *vapic_page;
 	u16 status;
 
-	if (vmx->nested.pi_desc &&
-	    vmx->nested.pi_pending) {
-		vmx->nested.pi_pending = false;
-		if (!pi_test_and_clear_on(vmx->nested.pi_desc))
-			return;
-
-		max_irr = find_last_bit(
-			(unsigned long *)vmx->nested.pi_desc->pir, 256);
+	if (!vmx->nested.pi_desc || !vmx->nested.pi_pending)
+		return;
 
-		if (max_irr == 256)
-			return;
+	vmx->nested.pi_pending = false;
+	if (!pi_test_and_clear_on(vmx->nested.pi_desc))
+		return;
 
+	max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
+	if (max_irr != 256) {
 		vapic_page = kmap(vmx->nested.virtual_apic_page);
 		__kvm_apic_update_irr(vmx->nested.pi_desc->pir, vapic_page);
 		kunmap(vmx->nested.virtual_apic_page);
@@ -4985,6 +5044,8 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 			vmcs_write16(GUEST_INTR_STATUS, status);
 		}
 	}
+
+	nested_mark_vmcs12_pages_dirty(vcpu);
 }
 
 static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
@@ -7134,34 +7195,32 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
+{
+	vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS);
+	vmcs_write64(VMCS_LINK_POINTER, -1ull);
+}
+
 static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
 {
 	if (vmx->nested.current_vmptr == -1ull)
 		return;
 
-	/* current_vmptr and current_vmcs12 are always set/reset together */
-	if (WARN_ON(vmx->nested.current_vmcs12 == NULL))
-		return;
-
 	if (enable_shadow_vmcs) {
 		/* copy to memory all shadowed fields in case
 		   they were modified */
 		copy_shadow_to_vmcs12(vmx);
 		vmx->nested.sync_shadow_vmcs = false;
-		vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
-				SECONDARY_EXEC_SHADOW_VMCS);
-		vmcs_write64(VMCS_LINK_POINTER, -1ull);
+		vmx_disable_shadow_vmcs(vmx);
 	}
 	vmx->nested.posted_intr_nv = -1;
 
 	/* Flush VMCS12 to guest memory */
-	memcpy(vmx->nested.current_vmcs12, vmx->nested.cached_vmcs12,
-	       VMCS12_SIZE);
+	kvm_vcpu_write_guest_page(&vmx->vcpu,
+				  vmx->nested.current_vmptr >> PAGE_SHIFT,
+				  vmx->nested.cached_vmcs12, 0, VMCS12_SIZE);
 
-	kunmap(vmx->nested.current_vmcs12_page);
-	nested_release_page(vmx->nested.current_vmcs12_page);
 	vmx->nested.current_vmptr = -1ull;
-	vmx->nested.current_vmcs12 = NULL;
 }
 
 /*
@@ -7175,12 +7234,14 @@ static void free_nested(struct vcpu_vmx *vmx)
 
 	vmx->nested.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
-	nested_release_vmcs12(vmx);
+	vmx->nested.posted_intr_nv = -1;
+	vmx->nested.current_vmptr = -1ull;
 	if (vmx->nested.msr_bitmap) {
 		free_page((unsigned long)vmx->nested.msr_bitmap);
 		vmx->nested.msr_bitmap = NULL;
 	}
 	if (enable_shadow_vmcs) {
+		vmx_disable_shadow_vmcs(vmx);
 		vmcs_clear(vmx->vmcs01.shadow_vmcs);
 		free_vmcs(vmx->vmcs01.shadow_vmcs);
 		vmx->vmcs01.shadow_vmcs = NULL;
@@ -7579,14 +7640,14 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		}
 
 		nested_release_vmcs12(vmx);
-		vmx->nested.current_vmcs12 = new_vmcs12;
-		vmx->nested.current_vmcs12_page = page;
 		/*
 		 * Load VMCS12 from guest memory since it is not already
 		 * cached.
 		 */
-		memcpy(vmx->nested.cached_vmcs12,
-		       vmx->nested.current_vmcs12, VMCS12_SIZE);
+		memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
+		kunmap(page);
+		nested_release_page_clean(page);
+
 		set_current_vmptr(vmx, vmptr);
 	}
 
@@ -8019,12 +8080,11 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
  * should handle it ourselves in L0 (and then continue L2). Only call this
  * when in is_guest_mode (L2).
  */
-static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
+static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 {
 	u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	u32 exit_reason = vmx->exit_reason;
 
 	trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason,
 				vmcs_readl(EXIT_QUALIFICATION),
@@ -8033,6 +8093,18 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
 				KVM_ISA_VMX);
 
+	/*
+	 * The host physical addresses of some pages of guest memory
+	 * are loaded into VMCS02 (e.g. L1's Virtual APIC Page). The CPU
+	 * may write to these pages via their host physical address while
+	 * L2 is running, bypassing any address-translation-based dirty
+	 * tracking (e.g. EPT write protection).
+	 *
+	 * Mark them dirty on every exit from L2 to prevent them from
+	 * getting out of sync with dirty tracking.
+	 */
+	nested_mark_vmcs12_pages_dirty(vcpu);
+
 	if (vmx->nested.nested_run_pending)
 		return false;
 
@@ -8169,6 +8241,29 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 	}
 }
 
+static int nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason)
+{
+	u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+
+	/*
+	 * At this point, the exit interruption info in exit_intr_info
+	 * is only valid for EXCEPTION_NMI exits.  For EXTERNAL_INTERRUPT
+	 * we need to query the in-kernel LAPIC.
+	 */
+	WARN_ON(exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT);
+	if ((exit_intr_info &
+	     (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
+	    (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) {
+		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+		vmcs12->vm_exit_intr_error_code =
+			vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+	}
+
+	nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info,
+			  vmcs_readl(EXIT_QUALIFICATION));
+	return 1;
+}
+
 static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 {
 	*info1 = vmcs_readl(EXIT_QUALIFICATION);
@@ -8415,12 +8510,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	if (vmx->emulation_required)
 		return handle_invalid_guest_state(vcpu);
 
-	if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) {
-		nested_vmx_vmexit(vcpu, exit_reason,
-				  vmcs_read32(VM_EXIT_INTR_INFO),
-				  vmcs_readl(EXIT_QUALIFICATION));
-		return 1;
-	}
+	if (is_guest_mode(vcpu) && nested_vmx_exit_reflected(vcpu, exit_reason))
+		return nested_vmx_reflect_vmexit(vcpu, exit_reason);
 
 	if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
 		dump_vmcs();
@@ -9223,7 +9314,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
-	vmx->nested.current_vmcs12 = NULL;
 
 	vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
 
@@ -9509,12 +9599,15 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
 
 	WARN_ON(!is_guest_mode(vcpu));
 
-	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code))
-		nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
-				  vmcs_read32(VM_EXIT_INTR_INFO),
-				  vmcs_readl(EXIT_QUALIFICATION));
-	else
+	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) {
+		vmcs12->vm_exit_intr_error_code = fault->error_code;
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
+				  PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
+				  INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
+				  fault->address);
+	} else {
 		kvm_inject_page_fault(vcpu, fault);
+	}
 }
 
 static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
@@ -10094,12 +10187,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
 	 * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
 	 * !enable_ept, EB.PF is 1, so the "or" will always be 1.
-	 *
-	 * A problem with this approach (when !enable_ept) is that L1 may be
-	 * injected with more page faults than it asked for. This could have
-	 * caused problems, but in practice existing hypervisors don't care.
-	 * To fix this, we will need to emulate the PFEC checking (on the L1
-	 * page tables), using walk_addr(), when injecting PFs to L1.
 	 */
 	vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
 		enable_ept ? vmcs12->page_fault_error_code_mask : 0);
@@ -10847,13 +10934,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	vmcs12->vm_exit_reason = exit_reason;
 	vmcs12->exit_qualification = exit_qualification;
-
 	vmcs12->vm_exit_intr_info = exit_intr_info;
-	if ((vmcs12->vm_exit_intr_info &
-	     (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
-	    (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK))
-		vmcs12->vm_exit_intr_error_code =
-			vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+
 	vmcs12->idt_vectoring_info_field = 0;
 	vmcs12->vm_exit_instruction_len = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
 	vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
@@ -11049,8 +11131,15 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 
 	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 
-	if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
-	    && nested_exit_intr_ack_set(vcpu)) {
+	/*
+	 * TODO: SDM says that with acknowledge interrupt on exit, bit 31 of
+	 * the VM-exit interrupt information (valid interrupt) is always set to
+	 * 1 on EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't need
+	 * kvm_cpu_has_interrupt().  See the commit message for details.
+	 */
+	if (nested_exit_intr_ack_set(vcpu) &&
+	    exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
+	    kvm_cpu_has_interrupt(vcpu)) {
 		int irq = kvm_cpu_get_interrupt(vcpu);
 		WARN_ON(irq < 0);
 		vmcs12->vm_exit_intr_info = irq |
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6c97c82814c4..d734aa8c5b4f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3159,15 +3159,18 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		kvm_set_hflags(vcpu, hflags);
 
 		vcpu->arch.smi_pending = events->smi.pending;
-		if (events->smi.smm_inside_nmi)
-			vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
-		else
-			vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
-		if (lapic_in_kernel(vcpu)) {
-			if (events->smi.latched_init)
-				set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+
+		if (events->smi.smm) {
+			if (events->smi.smm_inside_nmi)
+				vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
 			else
-				clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+				vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
+			if (lapic_in_kernel(vcpu)) {
+				if (events->smi.latched_init)
+					set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+				else
+					clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
+			}
 		}
 	}
 
@@ -6215,6 +6218,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
 
 	lapic_irq.shorthand = 0;
 	lapic_irq.dest_mode = 0;
+	lapic_irq.level = 0;
 	lapic_irq.dest_id = apicid;
 	lapic_irq.msi_redir_hint = false;